INDEX

Explanations

mentions of federal and state governmental entities or policies

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ©

-0.86

hov

-0.73

eks

-0.72

ojure

-0.71

:[

-0.68

 Shiva

-0.65

 Guilty

-0.64

 Dracula

-0.63

forts

-0.63

ãĤ£

-0.62

POSITIVE LOGITS

rogens

1.09

rogen

1.04

 allied

0.78

non

0.71

 unarmed

0.71

 continental

0.71

 nons

0.70

 rebellious

0.69

 intermediate

0.69

organic

0.68

Activations Density 0.218%

mentions of federal and state governmental entities or policies

the conjunction "and" in various contexts

No Comments

No Known Activations